Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2889 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6969. Min Range: -6.6969
Max Act: 6.6969. Min Act: -0.1700
Data Index: 5538565 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6969. Min Range: -6.6969
Max Act: 6.0094. Min Act: -0.1700
Data Index: 7755331 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6969. Min Range: -6.6969
Max Act: 6.0094. Min Act: -0.1700
Data Index: 5396217 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6969. Min Range: -6.6969
Max Act: 6.0094. Min Act: -0.1700
Data Index: 1515907 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.9469. Min Act: -0.1700
Data Index: 6926795 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.9469. Min Act: -0.1700
Data Index: 2361467 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.8844. Min Act: -0.1700
Data Index: 895977 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.8844. Min Act: -0.1700
Data Index: 1231774 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.8531. Min Act: -0.1700
Data Index: 5206041 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.8531. Min Act: -0.1700
Data Index: 676411 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.8531. Min Act: -0.1700
Data Index: 5342051 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.8219. Min Act: -0.1700
Data Index: 6051111 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.8219. Min Act: -0.1700
Data Index: 4917251 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.8219. Min Act: -0.1700
Data Index: 6324099 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.7906. Min Act: -0.1700
Data Index: 5763632 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.7906. Min Act: -0.1700
Data Index: 8035068 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.7281. Min Act: -0.1700
Data Index: 7140561 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.7594. Min Act: -0.1700
Data Index: 5183407 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.7594. Min Act: -0.1700
Data Index: 5141075 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6969. Min Range: -6.6969
Max Act: 5.7594. Min Act: -0.1700
Data Index: 5496264 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19